Files
FYS-STK4155/doc/pub/week46/html/._week46-bs026.html
Morten Hjorth-Jensen 2c1f27b519 update
2023-11-16 06:33:54 +01:00

390 lines
24 KiB
HTML

<!--
HTML file automatically generated from DocOnce source
(https://github.com/doconce/doconce/)
doconce format html week46.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week46-bs --no_mako
-->
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name="generator" content="DocOnce: https://github.com/doconce/doconce/" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<meta name="description" content="Week 46: Decision Trees, Ensemble methods and Random Forests">
<title>Week 46: Decision Trees, Ensemble methods and Random Forests</title>
<!-- Bootstrap style: bootstrap -->
<!-- doconce format html week46.do.txt --html_style=bootstrap --pygments_html_style=default --html_admon=bootstrap_panel --html_output=week46-bs --no_mako -->
<link href="https://netdna.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet">
<!-- not necessary
<link href="https://netdna.bootstrapcdn.com/font-awesome/4.0.3/css/font-awesome.css" rel="stylesheet">
-->
<style type="text/css">
/* Add scrollbar to dropdown menus in bootstrap navigation bar */
.dropdown-menu {
height: auto;
max-height: 400px;
overflow-x: hidden;
}
/* Adds an invisible element before each target to offset for the navigation
bar */
.anchor::before {
content:"";
display:block;
height:50px; /* fixed header height for style bootstrap */
margin:-50px 0 0; /* negative fixed header height */
}
</style>
</head>
<!-- tocinfo
{'highest level': 2,
'sections': [('Plan for week 46', 2, None, 'plan-for-week-46'),
('Decision trees, overarching aims',
2,
None,
'decision-trees-overarching-aims'),
('Basics of a tree', 2, None, 'basics-of-a-tree'),
('A typical Decision Tree with its pertinent Jargon, '
'Classification Problem',
2,
None,
'a-typical-decision-tree-with-its-pertinent-jargon-classification-problem'),
('General Features', 2, None, 'general-features'),
('How do we set it up?', 2, None, 'how-do-we-set-it-up'),
('Decision trees and Regression',
2,
None,
'decision-trees-and-regression'),
('Building a tree, regression',
2,
None,
'building-a-tree-regression'),
('A top-down approach, recursive binary splitting',
2,
None,
'a-top-down-approach-recursive-binary-splitting'),
('Making a tree', 2, None, 'making-a-tree'),
('Pruning the tree', 2, None, 'pruning-the-tree'),
('Cost complexity pruning', 2, None, 'cost-complexity-pruning'),
('Schematic Regression Procedure',
2,
None,
'schematic-regression-procedure'),
('A Classification Tree', 2, None, 'a-classification-tree'),
('Growing a classification tree',
2,
None,
'growing-a-classification-tree'),
('Classification tree, how to split nodes',
2,
None,
'classification-tree-how-to-split-nodes'),
('Visualizing the Tree, Classification',
2,
None,
'visualizing-the-tree-classification'),
('Visualizing the Tree, The Moons',
2,
None,
'visualizing-the-tree-the-moons'),
('Other ways of visualizing the trees',
2,
None,
'other-ways-of-visualizing-the-trees'),
('Printing out as text', 2, None, 'printing-out-as-text'),
('Algorithms for Setting up Decision Trees',
2,
None,
'algorithms-for-setting-up-decision-trees'),
('The CART algorithm for Classification',
2,
None,
'the-cart-algorithm-for-classification'),
('The CART algorithm for Regression',
2,
None,
'the-cart-algorithm-for-regression'),
('Why binary splits?', 2, None, 'why-binary-splits'),
('Computing a Tree using the Gini Index',
2,
None,
'computing-a-tree-using-the-gini-index'),
('The Table', 2, None, 'the-table'),
('Computing the various Gini Indices',
2,
None,
'computing-the-various-gini-indices'),
('Computing the various Gini Indices, Hours slept',
2,
None,
'computing-the-various-gini-indices-hours-slept'),
('Computing the various Gini Indices, Hours studied',
2,
None,
'computing-the-various-gini-indices-hours-studied'),
('A possible code using Scikit-Learn',
2,
None,
'a-possible-code-using-scikit-learn'),
('Further example: Computing the Gini index',
2,
None,
'further-example-computing-the-gini-index'),
('Simple Python Code to read in Data and perform Classification',
2,
None,
'simple-python-code-to-read-in-data-and-perform-classification'),
('Computing the Gini Factor',
2,
None,
'computing-the-gini-factor'),
('Regression trees', 2, None, 'regression-trees'),
('Final regressor code', 2, None, 'final-regressor-code'),
('Pros and cons of trees, pros',
2,
None,
'pros-and-cons-of-trees-pros'),
('Disadvantages', 2, None, 'disadvantages'),
('Ensemble Methods: From a Single Tree to Many Trees and Extreme '
'Boosting, Meet the Jungle of Methods',
2,
None,
'ensemble-methods-from-a-single-tree-to-many-trees-and-extreme-boosting-meet-the-jungle-of-methods'),
('An Overview of Ensemble Methods',
2,
None,
'an-overview-of-ensemble-methods'),
('Why Voting?', 2, None, 'why-voting'),
('Tossing coins', 2, None, 'tossing-coins'),
('Standard imports first', 2, None, 'standard-imports-first'),
('Simple Voting Example, head or tail',
2,
None,
'simple-voting-example-head-or-tail'),
('Using the Voting Classifier',
2,
None,
'using-the-voting-classifier'),
('Voting and Bagging', 2, None, 'voting-and-bagging'),
('Bagging', 2, None, 'bagging'),
('More bagging', 2, None, 'more-bagging'),
('Making your own Bootstrap: Changing the Level of the Decision '
'Tree',
2,
None,
'making-your-own-bootstrap-changing-the-level-of-the-decision-tree'),
('Random forests', 2, None, 'random-forests'),
('Random Forest Algorithm', 2, None, 'random-forest-algorithm'),
('Random Forests Compared with other Methods on the Cancer Data',
2,
None,
'random-forests-compared-with-other-methods-on-the-cancer-data'),
('Compare Bagging on Trees with Random Forests',
2,
None,
'compare-bagging-on-trees-with-random-forests'),
("Boosting, a Bird's Eye View",
2,
None,
'boosting-a-bird-s-eye-view'),
('What is boosting? Additive Modelling/Iterative Fitting',
2,
None,
'what-is-boosting-additive-modelling-iterative-fitting'),
('Iterative Fitting, Regression and Squared-error Cost Function',
2,
None,
'iterative-fitting-regression-and-squared-error-cost-function'),
('Squared-Error Example and Iterative Fitting',
2,
None,
'squared-error-example-and-iterative-fitting'),
('Iterative Fitting, Classification and AdaBoost',
2,
None,
'iterative-fitting-classification-and-adaboost'),
('Adaptive Boosting, AdaBoost',
2,
None,
'adaptive-boosting-adaboost'),
('Building up AdaBoost', 2, None, 'building-up-adaboost'),
('Adaptive boosting: AdaBoost, Basic Algorithm',
2,
None,
'adaptive-boosting-adaboost-basic-algorithm'),
('Basic Steps of AdaBoost', 2, None, 'basic-steps-of-adaboost'),
('AdaBoost Examples', 2, None, 'adaboost-examples')]}
end of tocinfo -->
<body>
<script type="text/x-mathjax-config">
MathJax.Hub.Config({
TeX: {
equationNumbers: { autoNumber: "none" },
extensions: ["AMSmath.js", "AMSsymbols.js", "autobold.js", "color.js"]
}
});
</script>
<script type="text/javascript" async
src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML">
</script>
<!-- Bootstrap navigation bar -->
<div class="navbar navbar-default navbar-fixed-top">
<div class="navbar-header">
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".navbar-responsive-collapse">
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<a class="navbar-brand" href="week46-bs.html">Week 46: Decision Trees, Ensemble methods and Random Forests</a>
</div>
<div class="navbar-collapse collapse navbar-responsive-collapse">
<ul class="nav navbar-nav navbar-right">
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown">Contents <b class="caret"></b></a>
<ul class="dropdown-menu">
<!-- navigation toc: --> <li><a href="._week46-bs001.html#plan-for-week-46" style="font-size: 80%;">Plan for week 46</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs002.html#decision-trees-overarching-aims" style="font-size: 80%;">Decision trees, overarching aims</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs003.html#basics-of-a-tree" style="font-size: 80%;">Basics of a tree</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs004.html#a-typical-decision-tree-with-its-pertinent-jargon-classification-problem" style="font-size: 80%;">A typical Decision Tree with its pertinent Jargon, Classification Problem</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs005.html#general-features" style="font-size: 80%;">General Features</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs006.html#how-do-we-set-it-up" style="font-size: 80%;">How do we set it up?</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs007.html#decision-trees-and-regression" style="font-size: 80%;">Decision trees and Regression</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs008.html#building-a-tree-regression" style="font-size: 80%;">Building a tree, regression</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs009.html#a-top-down-approach-recursive-binary-splitting" style="font-size: 80%;">A top-down approach, recursive binary splitting</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs010.html#making-a-tree" style="font-size: 80%;">Making a tree</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs011.html#pruning-the-tree" style="font-size: 80%;">Pruning the tree</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs012.html#cost-complexity-pruning" style="font-size: 80%;">Cost complexity pruning</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs013.html#schematic-regression-procedure" style="font-size: 80%;">Schematic Regression Procedure</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs014.html#a-classification-tree" style="font-size: 80%;">A Classification Tree</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs015.html#growing-a-classification-tree" style="font-size: 80%;">Growing a classification tree</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs016.html#classification-tree-how-to-split-nodes" style="font-size: 80%;">Classification tree, how to split nodes</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs017.html#visualizing-the-tree-classification" style="font-size: 80%;">Visualizing the Tree, Classification</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs018.html#visualizing-the-tree-the-moons" style="font-size: 80%;">Visualizing the Tree, The Moons</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs019.html#other-ways-of-visualizing-the-trees" style="font-size: 80%;">Other ways of visualizing the trees</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs020.html#printing-out-as-text" style="font-size: 80%;">Printing out as text</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs021.html#algorithms-for-setting-up-decision-trees" style="font-size: 80%;">Algorithms for Setting up Decision Trees</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs022.html#the-cart-algorithm-for-classification" style="font-size: 80%;">The CART algorithm for Classification</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs023.html#the-cart-algorithm-for-regression" style="font-size: 80%;">The CART algorithm for Regression</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs024.html#why-binary-splits" style="font-size: 80%;">Why binary splits?</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs025.html#computing-a-tree-using-the-gini-index" style="font-size: 80%;">Computing a Tree using the Gini Index</a></li>
<!-- navigation toc: --> <li><a href="#the-table" style="font-size: 80%;">The Table</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs027.html#computing-the-various-gini-indices" style="font-size: 80%;">Computing the various Gini Indices</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs028.html#computing-the-various-gini-indices-hours-slept" style="font-size: 80%;">Computing the various Gini Indices, Hours slept</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs029.html#computing-the-various-gini-indices-hours-studied" style="font-size: 80%;">Computing the various Gini Indices, Hours studied</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs030.html#a-possible-code-using-scikit-learn" style="font-size: 80%;">A possible code using Scikit-Learn</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs031.html#further-example-computing-the-gini-index" style="font-size: 80%;">Further example: Computing the Gini index</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs032.html#simple-python-code-to-read-in-data-and-perform-classification" style="font-size: 80%;">Simple Python Code to read in Data and perform Classification</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs033.html#computing-the-gini-factor" style="font-size: 80%;">Computing the Gini Factor</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs034.html#regression-trees" style="font-size: 80%;">Regression trees</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs035.html#final-regressor-code" style="font-size: 80%;">Final regressor code</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs036.html#pros-and-cons-of-trees-pros" style="font-size: 80%;">Pros and cons of trees, pros</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs037.html#disadvantages" style="font-size: 80%;">Disadvantages</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs038.html#ensemble-methods-from-a-single-tree-to-many-trees-and-extreme-boosting-meet-the-jungle-of-methods" style="font-size: 80%;">Ensemble Methods: From a Single Tree to Many Trees and Extreme Boosting, Meet the Jungle of Methods</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs039.html#an-overview-of-ensemble-methods" style="font-size: 80%;">An Overview of Ensemble Methods</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs040.html#why-voting" style="font-size: 80%;">Why Voting?</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs041.html#tossing-coins" style="font-size: 80%;">Tossing coins</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs042.html#standard-imports-first" style="font-size: 80%;">Standard imports first</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs043.html#simple-voting-example-head-or-tail" style="font-size: 80%;">Simple Voting Example, head or tail</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs044.html#using-the-voting-classifier" style="font-size: 80%;">Using the Voting Classifier</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs045.html#voting-and-bagging" style="font-size: 80%;">Voting and Bagging</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs046.html#bagging" style="font-size: 80%;">Bagging</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs047.html#more-bagging" style="font-size: 80%;">More bagging</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs048.html#making-your-own-bootstrap-changing-the-level-of-the-decision-tree" style="font-size: 80%;">Making your own Bootstrap: Changing the Level of the Decision Tree</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs049.html#random-forests" style="font-size: 80%;">Random forests</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs050.html#random-forest-algorithm" style="font-size: 80%;">Random Forest Algorithm</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs051.html#random-forests-compared-with-other-methods-on-the-cancer-data" style="font-size: 80%;">Random Forests Compared with other Methods on the Cancer Data</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs052.html#compare-bagging-on-trees-with-random-forests" style="font-size: 80%;">Compare Bagging on Trees with Random Forests</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs053.html#boosting-a-bird-s-eye-view" style="font-size: 80%;">Boosting, a Bird's Eye View</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs054.html#what-is-boosting-additive-modelling-iterative-fitting" style="font-size: 80%;">What is boosting? Additive Modelling/Iterative Fitting</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs055.html#iterative-fitting-regression-and-squared-error-cost-function" style="font-size: 80%;">Iterative Fitting, Regression and Squared-error Cost Function</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs056.html#squared-error-example-and-iterative-fitting" style="font-size: 80%;">Squared-Error Example and Iterative Fitting</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs057.html#iterative-fitting-classification-and-adaboost" style="font-size: 80%;">Iterative Fitting, Classification and AdaBoost</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs058.html#adaptive-boosting-adaboost" style="font-size: 80%;">Adaptive Boosting, AdaBoost</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs059.html#building-up-adaboost" style="font-size: 80%;">Building up AdaBoost</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs060.html#adaptive-boosting-adaboost-basic-algorithm" style="font-size: 80%;">Adaptive boosting: AdaBoost, Basic Algorithm</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs061.html#basic-steps-of-adaboost" style="font-size: 80%;">Basic Steps of AdaBoost</a></li>
<!-- navigation toc: --> <li><a href="._week46-bs062.html#adaboost-examples" style="font-size: 80%;">AdaBoost Examples</a></li>
</ul>
</li>
</ul>
</div>
</div>
</div> <!-- end of navigation bar -->
<div class="container">
<p>&nbsp;</p><p>&nbsp;</p><p>&nbsp;</p> <!-- add vertical space -->
<a name="part0026"></a>
<!-- !split -->
<h2 id="the-table" class="anchor">The Table </h2>
<div class="row">
<div class="col-xs-4">
<table class="dotable table-striped table-hover table-condensed">
<thead>
<tr><td align="center"><b>Grade Trend</b></td> <td align="center"><b>Hours slept</b></td> <td align="center"><b>Hours Studied</b></td> <td align="center"><b>Grade</b></td> </tr>
</thead>
<tbody>
<tr><td align="center"> Above </td> <td align="center"> Low </td> <td align="center"> High </td> <td align="center"> Above </td> </tr>
<tr><td align="center"> Below </td> <td align="center"> High </td> <td align="center"> Low </td> <td align="center"> Below </td> </tr>
<tr><td align="center"> Above </td> <td align="center"> Low </td> <td align="center"> High </td> <td align="center"> Above </td> </tr>
<tr><td align="center"> Above </td> <td align="center"> High </td> <td align="center"> High </td> <td align="center"> Above </td> </tr>
<tr><td align="center"> Below </td> <td align="center"> Low </td> <td align="center"> High </td> <td align="center"> Below </td> </tr>
<tr><td align="center"> Above </td> <td align="center"> Low </td> <td align="center"> Low </td> <td align="center"> Below </td> </tr>
<tr><td align="center"> Below </td> <td align="center"> High </td> <td align="center"> High </td> <td align="center"> Below </td> </tr>
<tr><td align="center"> Below </td> <td align="center"> Low </td> <td align="center"> High </td> <td align="center"> Below </td> </tr>
<tr><td align="center"> Above </td> <td align="center"> Low </td> <td align="center"> Low </td> <td align="center"> Below </td> </tr>
<tr><td align="center"> Above </td> <td align="center"> High </td> <td align="center"> High </td> <td align="center"> Above </td> </tr>
</tbody>
</table>
</div> <!-- col-xs-4 -->
</div> <!-- cell row -->
<p>
<!-- navigation buttons at the bottom of the page -->
<ul class="pagination">
<li><a href="._week46-bs025.html">&laquo;</a></li>
<li><a href="._week46-bs000.html">1</a></li>
<li><a href="">...</a></li>
<li><a href="._week46-bs018.html">19</a></li>
<li><a href="._week46-bs019.html">20</a></li>
<li><a href="._week46-bs020.html">21</a></li>
<li><a href="._week46-bs021.html">22</a></li>
<li><a href="._week46-bs022.html">23</a></li>
<li><a href="._week46-bs023.html">24</a></li>
<li><a href="._week46-bs024.html">25</a></li>
<li><a href="._week46-bs025.html">26</a></li>
<li class="active"><a href="._week46-bs026.html">27</a></li>
<li><a href="._week46-bs027.html">28</a></li>
<li><a href="._week46-bs028.html">29</a></li>
<li><a href="._week46-bs029.html">30</a></li>
<li><a href="._week46-bs030.html">31</a></li>
<li><a href="._week46-bs031.html">32</a></li>
<li><a href="._week46-bs032.html">33</a></li>
<li><a href="._week46-bs033.html">34</a></li>
<li><a href="._week46-bs034.html">35</a></li>
<li><a href="._week46-bs035.html">36</a></li>
<li><a href="">...</a></li>
<li><a href="._week46-bs062.html">63</a></li>
<li><a href="._week46-bs027.html">&raquo;</a></li>
</ul>
<!-- ------------------- end of main content --------------- -->
</div> <!-- end container -->
<!-- include javascript, jQuery *first* -->
<script src="https://ajax.googleapis.com/ajax/libs/jquery/1.10.2/jquery.min.js"></script>
<script src="https://netdna.bootstrapcdn.com/bootstrap/3.0.0/js/bootstrap.min.js"></script>
<!-- Bootstrap footer
<footer>
<a href="https://..."><img width="250" align=right src="https://..."></a>
</footer>
-->
<center style="font-size:80%">
<!-- copyright only on the titlepage -->
</center>
</body>
</html>